whisper-small-zh

xmzhu/whisper-small-zh

whisper-small-zh is a automatic speech recognition model from xmzhu. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

1% of all-time downloads

All-time downloads

1.3K

Public

Repo size

5.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin967 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Dec 19, 2022
Updated: Dec 20, 2022
SHA: 1697878d

Datasets

mozilla-foundation/common_voice_11_0

Model card

From the Hugging Face model README

Whisper Small Chinese

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 zh-CN dataset. It achieves the following results on the evaluation set:

Loss: 0.3946
Wer: 72.3626

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 64
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5179	2.02	1000	0.3333	72.9831
0.1273	4.04	2000	0.3562	73.9621
0.0163	6.06	3000	0.3790	73.9708
0.004	8.07	4000	0.3946	72.3626
0.025	11.0	5000	0.4019	72.6772

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.7.1.dev0
Tokenizers 0.13.2

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Languages: zh
Created: Dec 19, 2022
Updated: Dec 20, 2022